Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mahmoud20138/Tradecraft --skill elliott-wave-enginegit clone --depth 1 https://github.com/mahmoud20138/TradecraftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mahmoud20138/tradecraft/elliott-wave-engine)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/elliott-wave-engine"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/elliott-wave-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/elliott-wave-engine"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/elliott-wave-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01017 |
| Opus 5 | $0.00046 | $0.00508 |
| Sonnet 5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
elliott-wave-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Elliott Wave Engine
import pandas as pd, numpy as np
from scipy.signal import argrelextrema
class ElliottWaveEngine:
@staticmethod
def find_waves(df: pd.DataFrame, order: int = 10) -> dict:
"""Attempt to identify Elliott Wave structure from swing points."""
highs_idx = argrelextrema(df["high"].values, np.greater, order=order)[0]
lows_idx = argrelextrema(df["low"].values, np.less, order=order)[0]
swings = []
for i in highs_idx:
swings.append({"idx": int(i), "price": df["high"].iloc[i], "type": "high", "time": df.index[i]})
for i in lows_idx:
swings.append({"idx": int(i), "price": df["low"].iloc[i], "type": "low", "time": df.index[i]})
swings.sort(key=lambda s: s["idx"])
# Validate impulse wave rules
waves = ElliottWaveEngine._classify_impulse(swings)
return {
"swings_found": len(swings),
"waves": waves,
"current_wave": waves[-1] if waves else None,
"note": "Elliott Waves are subjective. Multiple valid counts often exist. Use as confluence, not primary signal.",
}
@staticmethod
def _classify_impulse(swings: list) -> list:
"""Check if swing sequence follows 5-wave impulse rules."""
waves = []
if len(swings) < 5:
return [{"wave": "insufficient_data", "swings": len(swings)}]
for i in range(0, len(swings) - 4, 2):
s = swings[i:i+5]
if len(s) < 5: break
# Basic impulse: up-down-up-down-up (bullish) or reverse
is_bullish = s[0]["type"] == "low" and s[2]["price"] > s[0]["price"]
if is_bullish:
w3_longest = (s[2]["price"] - s[1]["price"]) > (s[0]["price"] if s[0]["type"]=="high" else 0)
w2_above_w1_start = s[1]["price"] > s[0]["price"]
waves.append({
"type": "impulse_bullish",
"wave_1": {"start": round(s[0]["price"], 5), "end": round(s[1]["price"], 5)},
"wave_2": {"start": round(s[1]["price"], 5), "end": round(s[2]["price"], 5) if len(s) > 2 else 0},
"w2_valid": w2_above_w1_start,
"position": i,
})
return waves if waves else [{"wave": "no_clear_impulse"}]
@staticmethod
def fibonacci_targets(wave_1_start: float, wave_1_end: float, wave_2_end: float) -> dict:
"""Project wave 3 and wave 5 targets using Fibonacci extensions."""
w1_range = abs(wave_1_end - wave_1_start)
direction = 1 if wave_1_end > wave_1_start else -1
return {
"wave_3_targets": {
"1.000": round(wave_2_end + direction * w1_range * 1.0, 5),
"1.618": round(wave_2_end + direction * w1_range * 1.618, 5),
"2.618": round(wave_2_end + direction * w1_range * 2.618, 5),
},
"wave_5_note": "Project from wave 4 end using wave 1 range",
"invalidation": round(wave_1_start, 5),
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 82 lines · 92 tokens per session scan A 98074b9d7413
elliott-wave-engine is a skill published in the GitHub repository mahmoud20138/Tradecraft (15 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 1,017 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
delu-oracle
Full-cognition token analysis for Base EVM tokens via the deluagent oracle. Pass a CA or cashtag, get back a flat decision header (action, conviction, entry/stop/size, read) plus full cognition report. Tiered x402 pricing — 100M+ DELU free, 50M+ 50k DELU, public 250k DELU. Sequential calls only.
correlation-analysis
Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation.
credit-analysis
A guide to analysing bonds and other fixed-income investments, including issuer credit quality, interest payments, default risk, credit spreads, and convertible bonds. It also covers Chinese fixed-income markets and local-government financing bonds.
correlation-regime
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs.
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.
risk-analysis
Risk measurement and stress testing — VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario stress testing.